Search

Background: We reported the concept of patient‐specific deep learning (DL) for real‐time markerless tumor segmentation in image‐guided radiotherapy (IGRT). The method was aimed to control the attention of convolutional neural networks (CNNs) by artificial differences in co‐occurrence probability (CoOCP) in training datasets, that is, focusing CNN attention on soft tissues while ignoring bones. However, the effectiveness of this attention‐based data augmentation has not been confirmed by explainable techniques. Furthermore, compared to reasonable ground truths, the feasibility of tumor segmentation in clinical kilovolt (kV) X‐ray fluoroscopic (XF) images has not been confirmed. Purpose: The first aim of this paper was to present evidence that the proposed method provides an explanation and control of DL behavior. The second purpose was to validate the real‐time lung tumor segmentation in clinical kV XF images for IGRT. Methods: This retrospective study included 10 patients with lung cancer. Patient‐specific and XF angle‐specific image pairs comprising digitally reconstructed radiographs (DRRs) and projected‐clinical‐target‐volume (pCTV) images were calculated from four‐dimensional computer tomographic data and treatment planning information. The training datasets were primarily augmented by random overlay (RO) and noise injection (NI): RO aims to differentiate positional CoOCP in soft tissues and bones, and NI aims to make a difference in the frequency of occurrence of local and global image features. The CNNs for each patient‐and‐angle were automatically optimized in the DL training stage to transform the training DRRs into pCTV images. In the inference stage, the trained CNNs transformed the test XF images into pCTV images, thus identifying target positions and shapes. Results: The visual analysis of DL attention heatmaps for a test image demonstrated that our method focused CNN attention on soft tissue and global image features rather than bones and local features. The processing time for each patient‐and‐angle‐specific dataset in the training stage was ∼30 min, whereas that in the inference stage was 8 ms/frame. The estimated three‐dimensional 95 percentile tracking error, Jaccard index, and Hausdorff distance for 10 patients were 1.3–3.9 mm, 0.85–0.94, and 0.6–4.9 mm, respectively. Conclusions: The proposed attention‐based data augmentation with both RO and NI made the CNN behavior more explainable and more controllable. The results obtained demonstrated the feasibility of real‐time markerless lung tumor segmentation in kV XF images for IGRT. [ABSTRACT FROM AUTHOR]

Purpose: In the modeling of beam data for proton therapy planning systems, absolute dose measurements are performed utilizing a Bragg peak chamber (BPC), which is a parallel-plate ionization chamber. The long-term stability of the BPC is crucial for ensuring accurate absolute dose measurement. The study aims to assess the long-term stability of the BPC in clinical proton pencil beam scanning delivery., Methods: The long-term stability evaluation focused on the BPC-Type 34070 (PTW Freiburg, Germany), utilizing clinical proton scanning beams from December 2022 to November 2023. Monthly investigations were conducted to evaluate the response and cross-calibration factor of the BPC and a reference chamber, employing the spread-out Bragg peak (SOBP) field. Additionally, assessments were made regarding the BPC's response to monoenergetic beams, along with an examination of the impact of polarity and ion recombination on the BPC., Results: The response and cross-calibration factor of the BPC varied up to 1.9% and 1.8%, respectively, while the response of the reference chamber remained within a 0.5% range. The BPC's response to the mono-energetic beams varied up to 2.0% across all energies, demonstrating similar variation trends in both the SOBP field and mono-energetic beams. Furthermore, the variations in polarity and ion recombination effect remained stable within a 0.4% range throughout the year. Notably, the reproducibility of the BPC remained high for each measurement conducted, whether for the SOBP field or mono-energetic beams, with a maximum deviation observed at 0.1%., Conclusions: The response and cross-calibration factor of the BPC demonstrated significant variations, with maximum changes of 1.9% and 1.8%, respectively. However, the reproducibility of the BPC remained consistently high for each measurement. It is recommended that when conducting absolute dose measurements using a BPC, its response should be compared and corrected against the reference chamber for each measurement., (© 2024 The Author(s). Journal of Applied Clinical Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Coincidence of the treatment and imaging isocenter coordinates is required to safely perform small-margin treatments, such as stereotactic radiosurgery of multiple brain metastases. A comprehensive and direct methodology for verifying concordance of kilovoltage cone-beam computed tomography (kV-CBCT) and treatment coordinates using an x-ray CT-based polymer gel dosimeter (dGEL) and onboard kV-CBCT was previously reported. Using this methodology, we tested the ability of a new commercially available x-ray CT-based polymer dGEL with a rapid response to provide efficient quality assurance (QA)., Purpose: The aim of this study was to evaluate the robustness of the three-dimensional geometric QA methodology using dGEL., Methods: The dGEL were commercially manufactured. The prescribed dose for each field was determined by visually identifying the 5, 10, and 20 Gy isodose lines. A linear accelerator was used to irradiate the gels with seven non-coplanar beams. An in-house analysis program was used to identify the beam axes and treatment isocenter in kV-CBCT coordinates by processing the pre- and post-irradiation CBCT images. The impact of the radiation dose on the test reproducibility was examined, and the detectability of an intentional geometric error was assessed., Results: The treatment isocenter was within 0.4 mm of the imaging isocenter for all radiation doses. The residual error of the test with the intentional error was within 0.2 mm. The analysis and image quality variations for a single dGEL introduced displacement errors less than 0.3 mm., Conclusions: The test assessed the coincidence of treatment and kV-CBCT isocenter coordinates and detected errors with high robustness. Even for a 10 Gy dose, the test yielded results comparable with those obtained using higher radiation doses owing to the rapid response of the dGEL dosimeter., (© 2024 The Author(s). Journal of Applied Clinical Medical Physics is published by Wiley Periodicals, Inc. on behalf of The American Association of Physicists in Medicine.)

Background/aim: This study pursued two goals: Firstly, to search for anatomical structures strongly correlating with dose deterioration, and secondly to investigate the effectiveness of image registration focusing on critical anatomy by comparing it with a conventional method. The aim was to achieve robust image registration to correct for anatomical changes during treatment., Patients and Methods: Twenty patients with head and neck cancer were enrolled, and 68 simulation computed tomography (CT) and rescan CT image sets were retrospectively analyzed. Forty volumetric-modulated arc therapy and intensity-modulated proton therapy plans were generated and recalculated according to the rescan CT to evaluate the dose effects of anatomical changes. Correlation coefficients were calculated for the relationships between the six-axis motion of the anatomy and the dose indices for the clinical target volume (CTV) and organs at risk. In the image registration, we compared a conventional method and target-based registration that limited the registration range to the CTV and vertebrae., Results: The CTV coverage and spinal cord dose were correlated with the position error associated with the pitch and vertical position of the vertebrae, and the parotid gland and oral cavity dose were strongly correlated with the position error associated with the roll of the clivus and mandible. The target registration improved CTV coverage and suppressed the increase in dose to organs at risk compared with conventional methods., Conclusion: Monitoring vertebral alignment, the assessment and correction of positioning errors associated with the clivus and mandible position errors are important to ensure the quality of daily treatment. Target-based registration may allow for more robust image registration., (Copyright © 2023 International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved.)